Abstract
Fire source distinction is useful in reducing the occurrence of false alarms and in choosing an effective fire extinguishing medium. This study was aimed at distinguishing fire sources through a smoke analysis. For this purpose, a smoke detection chamber was created, which was equipped with one light source and several light sensors for enabling simultaneous detection of light extinction and scattering, respectively. The test fires considered in this study had two kinds of sources: single fire source (paper, wood, and flammable liquid) and mixed fire source (paper-wood, paper-flammable liquid, and wood-flammable liquid mixtures). The amounts of extinction and scattering for each fire were measured experimentally, and the discrete probability distributions were calculated from the measured scattering amount. The optical characteristics of each fire were obtained using extinction data and the calculated probability distributions. These optical characteristics were then used for learning of neural networks, and the learned neural networks were used to distinguish fire sources from smoke generated in the case of both single fires and mixed fires. Results revealed that the neural networks could precisely distinguish fire sources on the basis of the smoke particles in the case of both single fires and mixed fires. The results of this study are expected to be useful in developing an advanced smoke detector that can distinguish fire sources in addition to detecting smoke.
Similar content being viewed by others
References
NFPA 72 (2010) National Fire Alarm and Signaling Code 2010 Edition
Jee SW, Lee CH, Kim SK, Lee JJ, Kim PY (2014) Development of a traceable fire alarm system based on the conventional fire alarm system. Fire Technol 50(3):805–822
Bukowski RW, Moore WD (2003) Fire alarm signaling systems, 3rd edn. NFPA Inc, pp 84–176
Arthur L, Danny P (2010) Smoke alarms—pilot study of nuisance alarms associated with cooking. U.S. Consumer Product Safety Commission
Liu Z, Kim AK (2003) Review of recent developments in fire detection technologies. J. Fire Prot Eng 13:129–151
Milke JA, Hulcher ME, Worrell CL (2003) Investigation of multi-sensor algorithms for fire detection. Fire Technol 39(4):363–382
Rose-Pehrsson SL, Hart SJ, Street TT, Williams FW, Hammond MH, Bottuk DT, Wright MT, Wong JT (2003) Early warning fire detection system using a probabilistic neural network. Fire Technol 39(2):147–171
Thuillard M (1994) New methods for reducing the number of false alarms in fire detection systems. Fire Technol 30(2):250–268
Derbel F (2004) Performance improvement of fire detectors by means of gas sensors and neural networks. Fire Saf J 39(5):383–398
Chen S-J, Hovde DC, Peterson KA, Marshall AW (2007) Fire detection using smoke and gas sensors. Fire Saf J 42(8):507–515
Jimin C, Jeonghwan L, Inhee L, Youngcheol C, Youngsin Y, Gunhee H (2009) A single-chip CMOS smoke and temperature sensor for an intelligent fire detector. IEEE Sens J 9(8):914–921
Loepfe M, Ryser P, Tompkin C, Wieser D (1997) Optical properties of fire and non-fire aerosols. Fire Saf J 29(2–3):185–194
Bukowski RW (1979) Smoke measurements in large- and small-scale fire testing—part I. Fire Technol 15(3):197–179
Bukowski RW (1979) Smoke measurements in large- and small-scale fire testing—part II. Fire Technol 15(4):271–281
Hinds WC (1995) Aerosol technology. Translation of Korean Language, ShinKwang MunHwa Publishing Co., pp 379–412
UL 268-2006 (2006) Smoke detectors for fire alarm signaling system
Kim DS (1995) Neural networks theory and applications. Hi-tech Press, pp 17–58
Acknowledgements
The author would like to thank Y. B. Kim for her valuable assistance.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jee, SW. Distinction of Fire Source from Smoke Using Discrete Probability Distribution and Neural Networks. Fire Technol 51, 887–904 (2015). https://doi.org/10.1007/s10694-014-0424-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10694-014-0424-3